CAD4TB has been developed by Delft Imaging in cooperation with Radboud Universiteit and the Lung Institute in Cape Town. The involvement of academic researchers from the beginning demonstrates the intention to deliver a high-quality and reliable product.
Click here to discover our comprehensive list of scientific publications on CAD4TB as of August 2023.
Publication highlights on CAD4TB Performance
- Newer version (CAD4TB 7) significantly outperformed the predecessor (CAD4TB 6), performing better than human readers and met WHO TPP values. [ZZ. Qin et al., PLOS Digital Health, 2022]
- CAD4TB v7 and two other CAD software solutions emerged from this evaluation as excellent alternatives for human CXR interpretation, performing on par with the Expert Reader and significantly better than the Intermediate Reader [Vietnam: A. Codlin et al., Nature Scientific Report, 2021]
- CAD4TB performs significantly better than human readers [Qin et al., The Lancet Digital Health, 2021] [Tanzania; Breuninger et al., PLOS One, 2014]
- CAD4TB is an accurate tool for community-based TB screening for prevalence survey in Kenya. CAD4TB 6 met the optimal WHO TPP (Target Product Profile) [Kenya: Mungai et al., medRxiv, 2021]
- CAD4TB on par with human expert readers [South Africa; Hogeweg et al., IEEE Trans Med Imaging, 2015], [Tanzania; Steiner et al., Public Health Action, 2015], [Zambia; Melendez et al., IJTLD, 2017], [London; Melendez et al., IJTLD, 2018], [the Philippines; Philipsen et al., IJTLD, 2019], [Pakistan; Murphy et al., Nature Scientific Reports, 2020] [South Africa; Fehr et al., NpJ, 2021], [Tavaziva et al., Clinical Infectious Diseases, 2021]
- CAD4TB met the WHO’s TPP at 90% sensitivity. [Qin et al., The Lancet Digital Health, 2021]
- In a community-based multi-disease screening survey in an HIV-endemic rural area, CAD4TB achieved comparable sensitivity and specificity to the radiologist. CAD4TB has potential to replace radiologists for triaging CXRs in prevalence surveys [South Africa: Fehr et al., npj digital medicine, 2021]
- In Tanzania, CAD4TB performance was significantly better than a clinical officer in [Tanzania: Breuninger et al., PLOS One, 2014]
Publication highlights on CAD4TB Efficiency
- The per-screen costs for the two CAD software programs that had a perpetual licensing costing structure are considerably lower than the cost with radiologists for high throughput in ACF scenarios. [S. Bashir. Et al., PLOS ONE, 2022]
- TB screening using Delft Light Backpack X-ray and CAD4TB during community-based ACF in hard-to-reach Niger Delta communities of Nigeria showed a high TB prevalence among participants. Nationwide deployment of the instrument in hard-to-reach areas is recommended. [B. Odume. et al., Public Health Action. 2022]
- CAD4TB v7 had a significantly higher AUC than v6, 0.903 (95% CI: 0.897–0.908) compared to 0.823 (0.816–0.830). CAD4TB 7 results in a steep initial increase of Xpert test saved. Until a threshold of 75, greater numbers of Xpert tests can be saved using CAD4TB v7. [ZZ. Qin et al., PLOS Digital Health, 2022]
- Using CAD4TB can save molecular tests such as Xpert tests. [Pakistan: Habib et al., Scientific Reports, 2020], [Qin et al., The Lancet Digital Health, 2021] [Pakistan: Zaidi et al., Nature Scientific Reports, 2018], [Bangladesh: T. Rahman et al., European Respiratory Journal, 2017]
- All five AI algorithms (incl. CAD4TB) significantly outperformed the radiologists and reduced the number of Xpert tests required by 50% while maintaining a sensitivity above 90%. [Qin et al., The Lancet Digital Health, 2021]
- Triage using AI-based CXR interpretation (incl. CAD4TB) can be cost-effective and even cost-saving relative to standard practice among persons with suspected TB in Pakistan. These results are likely applicable to other low-income, high-TB-burden settings. [Nsengiyumva et al. Open Forum Infectious Diseases, 2021]
- Community-based screening with innovative activities, comprising sensitive screening and diagnostic tools, including a digital X-ray and CAD4TB, effectively improves TB case detection. [Pakistan; A. Wali et al., Public Health Action, 2021]
- CAD4TB as a triage tool to pre-screen people with diabetes for Xpert testing can improve case-detection while potentially reducing program costs with more rational use of expensive molecular tests. [Pakistan; Habib et al., Nature Scientific Reports, 2020]
- In Pakistan, CAD4TB as a triage tool could minimize use of expensive molecular tests in low resource settings. [Pakistan; Murphy et al., Nature Scientific Reports, 2020]
- Used as a pre-screening system in TB-endemic regions, CAD4TB allows for testing of much larger numbers of subjects at a fraction of the cost. [Pakistan; Murphy et al., Nature Scientific Reports, 2020]
- In the Philippines, CAD4TB as a second reader showed 22% increase of TB detection and could help detect additional TB-positive cases that were initially missed at limited additional costs. [Philippines: Philipsen et al., IJTLD, 2019]
- In Pakistan, CAD4TB as a triage tool could minimize use of expensive molecular tests in low resource settings. [Pakistan; Zaidi et al., Nature Scientific Reports, 2018]
- Reduces cost per identified TB case and the cost per screened subject by almost half. [Philipsen et al., Nature Scientific Reports, 2015]
- Useful where trained human readers are scarce. [Muyoyeta et al., PLOS One, 2014]
Publication highlights on CAD4TB for HIV, Diabetes, Migrants, Paediatric TB & Prison-screening
TB/HIV
- In a community-based multi-disease screening survey in an HIV-endemic rural area, CAD4TB achieved comparable sensitivity and specificity to the radiologist. HIV serostatus did not impact CAD4TB’s performance. [South Africa: Fehr et al., npj digital medicine, 2021]
- Digital CXR using CAD4TB with universal HIV screening significantly increased timelines and completeness of HIV and TB diagnosis. [Malawi: MacPherson et al., PLOS MEDICINE, 2021]
- Combined use of mobile X-ray and CAD4TB to identify TB among high-risk groups to improve early TB diagnosis can deliver a major contribution to TB control in Romania. [Romania: B. Mahler et al., BMJ Open, 2021]
- In an HIV-negative population, CAD4TB v6 met WHO-recommended minimal accuracy for pulmonary tuberculosis triage tests. [F.A. Khan et al., The Lancet Digital Health, 2020]
Diabetes
- CAD4TB offers good diagnostic accuracy as triage for TB screening among diabetes patients [Habib et al., Nature Scientific Reports, 2020]
- CAD4TB with X-ray systems allowed not only rapid and systematic triage to Xpert testing, but also found quantitatively more TB-like abnormalities in those with Diabetes Mellitus In Bangladesh [Paul et al., Science Direct, 2020]
- CAD4TB has potential as a triage tool for TB screening in people living with diabetes, thereby significantly reducing the need for microbiological examination in Indonesia [Koesoemadinata et al., IJTLD, 2018]
Migrants
- CAD has the potential to be a useful additional diagnostic tool for paediatric TB by fine-tuning an existing algorithm with as little as several hundred well-classified paediatric chest x-rays. [South Africa: Palmer et al., PLOS Global Public Health, 2023]
Paediatric TB
- CAD may provide viable options for use in TB screening programs to increase TB detection, especially in low resource areas where there may be no available expert radiologists. [Gelaw et al., Plos Global Public Health, 2023]
Prison Screening
- Screening by mobile x-ray systems with automated interpretation could reduce the number of confirmatory tests required and enable screening to be more rapid in high burden TB settings, while still maintaining sufficient sensitivity. [Soares et al., The Lancet Regional Health – Americas, 2023]
- Inclusion of digital CXR to systematic TB screening detected additional TB cases among inmates that would otherwise have been missed, and using CAD4TB may also improve performance of screening algorithm. [Kim et al., IJTLD, 2020]
- High uptake of new screening tools such as digital X-ray with CAD4TB may be particularly feasible, reliable, and highly acceptable in prison settings. [Wali et al., BMC Public Health, 2019]
- CAD4TB reliably evaluates CXRs from a mostly asymptomatic prison population, with a performance comparable to local readers in Tanzania. [Steiner et al., Public Health Action, 2015]
Other
- WHO compendium of innovative health technologies for low-resource settings (CAD4TB on page 85).
- WHO global investments in tuberculosis research and developments (CAD4TB on page 30).
- Detecting TB in Zambia: determing the sensitivity and specifity of CAD4TB in comparison to GeneXpert testing. (The Sensitivity and Specificity of Using a Computer Aided Diagnosis Program for Automatically Scoring Chest X-Rays of Presumptive TB Patients Compared with Xpert MTB/RIF in Lusaka Zambia)
- Detecting TB in Tanzania: to assess the use of CAD4TB in a prison population. (Screening for pulmonary tuberculosis in a Tanzanian prison and computer-aided interpretation of chest X-rays)
- Detecting TB in Zambia: comparing the performance of CAD4TB in chest X-ray reading to radiologists.(Automatic versus human reading of chest X-rays in the Zambia National Tuberculosis Prevalence Survey)
- Mobile Care for TB Screening and Diagnosis – a How-To Guide. (USAID/CHallengeTB – 2018)
- Digital Imaging Innovations for Early TB Case Detection. (StopTB Partnership / CheckTB – November 2012)
- StopTB Partnership Field Guide on Chest X-ray Screening. (StopTB Partnership Field Guide on Chest X-ray Screening.)